Fast identification and susceptibility determination of E. coli isolated directly from patients' urine using infrared-spectroscopy and machine learning.
Spectrochim Acta A Mol Biomol Spectrosc
; 285: 121909, 2023 Jan 15.
Article
en En
| MEDLINE
| ID: mdl-36170776
ABSTRACT
For effective treatment, it is crucial to identify the infecting bacterium at the species level and to determine its antimicrobial susceptibility. This is especially true now, when numerous bacteria have developed multidrug resistance to most commonly used antibiotics. Currently used methods need â¼ 48 h to identify a bacterium and determine its susceptibility to specific antibiotics. This study reports the potential of using infrared spectroscopy with machine learning algorithms to identify E. coli isolated directly from patients' urine while simultaneously determining its susceptibility to antibiotics within â¼ 40 min after receiving the patient's urine sample. For this goal, 1,765 E. coli isolates purified directly from urine samples were collected from patients with urinary tract infections (UTIs). After collection, the samples were tested by infrared microscopy and analyzed by machine learning. We achieved success rates of â¼ 96% in isolate level identification and â¼ 84% in susceptibility determination.
Palabras clave
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Asunto principal:
Escherichia coli
/
Infecciones por Escherichia coli
Límite:
Humans
Idioma:
En
Revista:
Spectrochim Acta A Mol Biomol Spectrosc
Asunto de la revista:
BIOLOGIA MOLECULAR
Año:
2023
Tipo del documento:
Article
País de afiliación:
Israel